KLASIFIKASI IKLAN LOWONGAN KERJA MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM) DAN BORDERLINE SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE (BORDERLINE-SMOTE)

BERLIN, JERRY and Yusliani, Novi and Rodiah, Desty (2024) KLASIFIKASI IKLAN LOWONGAN KERJA MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM) DAN BORDERLINE SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE (BORDERLINE-SMOTE). Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021282025036.pdf] Text
RAMA_55201_09021282025036.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_TURNITIN.pdf] Text
RAMA_55201_09021282025036_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (7MB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_01_front_ref.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_02.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (735kB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_03.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (360kB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_04.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_05.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (269kB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_06.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (185kB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_07_lamp.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (179kB) | Request a copy
[thumbnail of RAMA_55201_09021282025036_0008118205_0021128905_08_ref.pdf] Text
RAMA_55201_09021282025036_0008118205_0021128905_08_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (196kB) | Request a copy

Abstract

The growth of the internet has made it easier to recruit workers through the publication of online job advertisements. However, this convenience also brings the risk of fraud in job advertisements that can harm both job seekers and companies. To overcome this problem, classification of job advertisements is required. One of the main challenges in text classification, especially in job advertisement data, is the significant imbalance of data between the majority and minority classes, with the majority class reaching 3500 data and the minority class only 500 data. This research aims to classify job advertisements using Support Vector Machine (SVM) and Borderline Synthetic Minority Over-Sampling Technique (Borderline-SMOTE) to overcome data imbalance. Tests were conducted to see the effect of job advertisements classification performance using SVM without Borderline-SMOTE and SVM with Borderline-SMOTE, where the parameter C used was 0.1, 0.25, 0.50, 0.75, and 1. The results showed that SVM with Borderline-SMOTE had better performance especially in recall and f-measure. In particular, at setting parameter C = 1 in SVM with Borderline-SMOTE, the most optimal results were obtained, with a precision value of 0.92, recall of 0.80, and f-measure of 0.86.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Borderline Synthetic Minority Over-Sampling Technique, Data Imbalance, Support Vector Machine, Text Classification
Subjects: P Language and Literature > P Philology. Linguistics > P98-98.5 Computational linguistics. Natural language processing
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Jerry Berlin
Date Deposited: 06 May 2024 07:17
Last Modified: 06 May 2024 07:17
URI: http://repository.unsri.ac.id/id/eprint/143696

Actions (login required)

View Item View Item